Sentiment classification of twitter data belonging to renewable energy using machine learning

Abstract

The paper disccuses about the sentimenal analysis process which is a classification problem. To study the emotions of people about alternate energy sources, we carried out sentiment analysis on Twitter data. Sentiment analysis is used to analyze opinions of the user for decision making with the help of natural language processing techniques. In this paper, we carried out sentiment analysis and classification task of tweets belonging to #RenewableEnergy. We applied five different machine learning algorithms for the classification of tweets into three categories. We have carried classification without feature selection technique and with feature selection techniques. We have used CfsSubsetEvaluation and Information Gain feature selection methods to reduce the number of features from the dataset. The result obtained through the techniques followed in this paper, shows that the accuracy of sentiment classification is better with feature selection methods. The best accuracy (92.96%) is achieved with Support Vector Machine(Using PUK Kernel) and CfsSubsetEval feature selection method.